|
Records |
Links |
|
Author |
Mikel Menta; Adriana Romero; Joost Van de Weijer |
![download PDF file pdf](img/file_PDF.gif)
|
|
Title |
Learning to adapt class-specific features across domains for semantic segmentation |
Type |
Miscellaneous |
|
Year |
2020 |
Publication ![sorted by Publication field, ascending order (up)](img/sort_asc.gif) |
Arxiv |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
arXiv:2001.08311
Recent advances in unsupervised domain adaptation have shown the effectiveness of adversarial training to adapt features across domains, endowing neural networks with the capability of being tested on a target domain without requiring any training annotations in this domain. The great majority of existing domain adaptation models rely on image translation networks, which often contain a huge amount of domain-specific parameters. Additionally, the feature adaptation step often happens globally, at a coarse level, hindering its applicability to tasks such as semantic segmentation, where details are of crucial importance to provide sharp results. In this thesis, we present a novel architecture, which learns to adapt features across domains by taking into account per class information. To that aim, we design a conditional pixel-wise discriminator network, whose output is conditioned on the segmentation masks. Moreover, following recent advances in image translation, we adopt the recently introduced StarGAN architecture as image translation backbone, since it is able to perform translations across multiple domains by means of a single generator network. Preliminary results on a segmentation task designed to assess the effectiveness of the proposed approach highlight the potential of the model, improving upon strong baselines and alternative designs. |
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
LAMP; 600.120 |
Approved |
no |
|
|
Call Number |
Admin @ si @ MRW2020 |
Serial |
3545 |
|
Permanent link to this record |
|
|
|
|
Author |
Pau Riba; Andreas Fischer; Josep Llados; Alicia Fornes |
![download PDF file pdf](img/file_PDF.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Learning Graph Edit Distance by Graph NeuralNetworks |
Type |
Miscellaneous |
|
Year |
2020 |
Publication ![sorted by Publication field, ascending order (up)](img/sort_asc.gif) |
Arxiv |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
The emergence of geometric deep learning as a novel framework to deal with graph-based representations has faded away traditional approaches in favor of completely new methodologies. In this paper, we propose a new framework able to combine the advances on deep metric learning with traditional approximations of the graph edit distance. Hence, we propose an efficient graph distance based on the novel field of geometric deep learning. Our method employs a message passing neural network to capture the graph structure, and thus, leveraging this information for its use on a distance computation. The performance of the proposed graph distance is validated on two different scenarios. On the one hand, in a graph retrieval of handwritten words~\ie~keyword spotting, showing its superior performance when compared with (approximate) graph edit distance benchmarks. On the other hand, demonstrating competitive results for graph similarity learning when compared with the current state-of-the-art on a recent benchmark dataset. |
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
DAG; 600.121; 600.140; 601.302 |
Approved |
no |
|
|
Call Number |
Admin @ si @ RFL2020 |
Serial |
3555 |
|
Permanent link to this record |
|
|
|
|
Author |
Wenlong Deng; Yongli Mou; Takahiro Kashiwa; Sergio Escalera; Kohei Nagai; Kotaro Nakayama; Yutaka Matsuo; Helmut Prendinger |
![goto web page url](img/www.gif)
|
|
Title |
Vision based Pixel-level Bridge Structural Damage Detection Using a Link ASPP Network |
Type |
Journal Article |
|
Year |
2020 |
Publication ![sorted by Publication field, ascending order (up)](img/sort_asc.gif) |
Automation in Construction |
Abbreviated Journal |
AC |
|
|
Volume |
110 |
Issue |
|
Pages |
102973 |
|
|
Keywords |
Semantic image segmentation; Deep learning |
|
|
Abstract |
Structural Health Monitoring (SHM) has greatly benefited from computer vision. Recently, deep learning approaches are widely used to accurately estimate the state of deterioration of infrastructure. In this work, we focus on the problem of bridge surface structural damage detection, such as delamination and rebar exposure. It is well known that the quality of a deep learning model is highly dependent on the quality of the training dataset. Bridge damage detection, our application domain, has the following main challenges: (i) labeling the damages requires knowledgeable civil engineering professionals, which makes it difficult to collect a large annotated dataset; (ii) the damage area could be very small, whereas the background area is large, which creates an unbalanced training environment; (iii) due to the difficulty to exactly determine the extension of the damage, there is often a variation among different labelers who perform pixel-wise labeling. In this paper, we propose a novel model for bridge structural damage detection to address the first two challenges. This paper follows the idea of an atrous spatial pyramid pooling (ASPP) module that is designed as a novel network for bridge damage detection. Further, we introduce the weight balanced Intersection over Union (IoU) loss function to achieve accurate segmentation on a highly unbalanced small dataset. The experimental results show that (i) the IoU loss function improves the overall performance of damage detection, as compared to cross entropy loss or focal loss, and (ii) the proposed model has a better ability to detect a minority class than other light segmentation networks. |
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
HuPBA; no proj |
Approved |
no |
|
|
Call Number |
Admin @ si @ DMK2020 |
Serial |
3314 |
|
Permanent link to this record |
|
|
|
|
Author |
Reza Azad; Maryam Asadi-Aghbolaghi; Mahmood Fathy; Sergio Escalera |
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Attention Deeplabv3+: Multi-level Context Attention Mechanism for Skin Lesion Segmentation |
Type |
Conference Article |
|
Year |
2020 |
Publication ![sorted by Publication field, ascending order (up)](img/sort_asc.gif) |
Bioimage computation workshop |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
|
|
|
Address |
Virtual; August 2020 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ECCVW |
|
|
Notes |
HUPBA |
Approved |
no |
|
|
Call Number |
Admin @ si @ AAF2020 |
Serial |
3520 |
|
Permanent link to this record |
|
|
|
|
Author |
Xialei Liu; Chenshen Wu; Mikel Menta; Luis Herranz; Bogdan Raducanu; Andrew Bagdanov; Shangling Jui; Joost Van de Weijer |
![download PDF file pdf](img/file_PDF.gif)
|
|
Title |
Generative Feature Replay for Class-Incremental Learning |
Type |
Conference Article |
|
Year |
2020 |
Publication ![sorted by Publication field, ascending order (up)](img/sort_asc.gif) |
CLVISION – Workshop on Continual Learning in Computer Vision |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
Humans are capable of learning new tasks without forgetting previous ones, while neural networks fail due to catastrophic forgetting between new and previously-learned tasks. We consider a class-incremental setting which means that the task-ID is unknown at inference time. The imbalance between old and new classes typically results in a bias of the network towards the newest ones. This imbalance problem can either be addressed by storing exemplars from previous tasks, or by using image replay methods. However, the latter can only be applied to toy datasets since image generation for complex datasets is a hard problem.
We propose a solution to the imbalance problem based on generative feature replay which does not require any exemplars. To do this, we split the network into two parts: a feature extractor and a classifier. To prevent forgetting, we combine generative feature replay in the classifier with feature distillation in the feature extractor. Through feature generation, our method reduces the complexity of generative replay and prevents the imbalance problem. Our approach is computationally efficient and scalable to large datasets. Experiments confirm that our approach achieves state-of-the-art results on CIFAR-100 and ImageNet, while requiring only a fraction of the storage needed for exemplar-based continual learning |
|
|
Address |
Virtual CVPR |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
CVPRW |
|
|
Notes |
LAMP; 601.309; 602.200; 600.141; 600.120 |
Approved |
no |
|
|
Call Number |
Admin @ si @ LWM2020 |
Serial |
3419 |
|
Permanent link to this record |
|
|
|
|
Author |
David Berga; Xavier Otazu |
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Computations of top-down attention by modulating V1 dynamics |
Type |
Conference Article |
|
Year |
2020 |
Publication ![sorted by Publication field, ascending order (up)](img/sort_asc.gif) |
Computational and Mathematical Models in Vision |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
|
|
|
Address |
St. Pete Beach; Florida; May 2020 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
MODVIS |
|
|
Notes |
NEUROBIT |
Approved |
no |
|
|
Call Number |
Admin @ si @ BeO2020a |
Serial |
3376 |
|
Permanent link to this record |
|
|
|
|
Author |
Yi Xiao; Felipe Codevilla; Christopher Pal; Antonio Lopez |
![download PDF file pdf](img/file_PDF.gif)
|
|
Title |
Action-Based Representation Learning for Autonomous Driving |
Type |
Conference Article |
|
Year |
2020 |
Publication ![sorted by Publication field, ascending order (up)](img/sort_asc.gif) |
Conference on Robot Learning |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
|
|
|
Abstract |
Human drivers produce a vast amount of data which could, in principle, be used to improve autonomous driving systems. Unfortunately, seemingly straightforward approaches for creating end-to-end driving models that map sensor data directly into driving actions are problematic in terms of interpretability, and typically have significant difficulty dealing with spurious correlations. Alternatively, we propose to use this kind of action-based driving data for learning representations. Our experiments show that an affordance-based driving model pre-trained with this approach can leverage a relatively small amount of weakly annotated imagery and outperform pure end-to-end driving models, while being more interpretable. Further, we demonstrate how this strategy outperforms previous methods based on learning inverse dynamics models as well as other methods based on heavy human supervision (ImageNet). |
|
|
Address |
virtual; November 2020 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
CORL |
|
|
Notes |
ADAS; 600.118 |
Approved |
no |
|
|
Call Number |
Admin @ si @ XCP2020 |
Serial |
3487 |
|
Permanent link to this record |
|
|
|
|
Author |
Beata Megyesi; Bernhard Esslinger; Alicia Fornes; Nils Kopal; Benedek Lang; George Lasry; Karl de Leeuw; Eva Pettersson; Arno Wacker; Michelle Waldispuhl |
![goto web page url](img/www.gif)
|
|
Title |
Decryption of historical manuscripts: the DECRYPT project |
Type |
Journal Article |
|
Year |
2020 |
Publication ![sorted by Publication field, ascending order (up)](img/sort_asc.gif) |
Cryptologia |
Abbreviated Journal |
CRYPT |
|
|
Volume |
44 |
Issue |
6 |
Pages |
545-559 |
|
|
Keywords |
automatic decryption; cipher collection; historical cryptology; image transcription |
|
|
Abstract |
Many historians and linguists are working individually and in an uncoordinated fashion on the identification and decryption of historical ciphers. This is a time-consuming process as they often work without access to automatic methods and processes that can accelerate the decipherment. At the same time, computer scientists and cryptologists are developing algorithms to decrypt various cipher types without having access to a large number of original ciphertexts. In this paper, we describe the DECRYPT project aiming at the creation of resources and tools for historical cryptology by bringing the expertise of various disciplines together for collecting data, exchanging methods for faster progress to transcribe, decrypt and contextualize historical encrypted manuscripts. We present our goals and work-in progress of a general approach for analyzing historical encrypted manuscripts using standardized methods and a new set of state-of-the-art tools. We release the data and tools as open-source hoping that all mentioned disciplines would benefit and contribute to the research infrastructure of historical cryptology. |
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
DAG; 600.140; 600.121 |
Approved |
no |
|
|
Call Number |
Admin @ si @ MEF2020 |
Serial |
3347 |
|
Permanent link to this record |
|
|
|
|
Author |
Tomas Sixta; Julio C. S. Jacques Junior; Pau Buch Cardona; Eduard Vazquez; Sergio Escalera |
![download PDF file pdf](img/file_PDF.gif)
![goto web page (via DOI) doi](img/doi.gif)
|
|
Title |
FairFace Challenge at ECCV 2020: Analyzing Bias in Face Recognition |
Type |
Conference Article |
|
Year |
2020 |
Publication ![sorted by Publication field, ascending order (up)](img/sort_asc.gif) |
ECCV Workshops |
Abbreviated Journal |
|
|
|
Volume |
12540 |
Issue |
|
Pages |
463-481 |
|
|
Keywords |
|
|
|
Abstract |
This work summarizes the 2020 ChaLearn Looking at People Fair Face Recognition and Analysis Challenge and provides a description of the top-winning solutions and analysis of the results. The aim of the challenge was to evaluate accuracy and bias in gender and skin colour of submitted algorithms on the task of 1:1 face verification in the presence of other confounding attributes. Participants were evaluated using an in-the-wild dataset based on reannotated IJB-C, further enriched 12.5K new images and additional labels. The dataset is not balanced, which simulates a real world scenario where AI-based models supposed to present fair outcomes are trained and evaluated on imbalanced data. The challenge attracted 151 participants, who made more 1.8K submissions in total. The final phase of the challenge attracted 36 active teams out of which 10 exceeded 0.999 AUC-ROC while achieving very low scores in the proposed bias metrics. Common strategies by the participants were face pre-processing, homogenization of data distributions, the use of bias aware loss functions and ensemble models. The analysis of top-10 teams shows higher false positive rates (and lower false negative rates) for females with dark skin tone as well as the potential of eyeglasses and young age to increase the false positive rates too. |
|
|
Address |
Virtual; August 2020 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ECCVW |
|
|
Notes |
HUPBA |
Approved |
no |
|
|
Call Number |
Admin @ si @ SJB2020 |
Serial |
3499 |
|
Permanent link to this record |
|
|
|
|
Author |
Martin Menchon; Estefania Talavera; Jose M. Massa; Petia Radeva |
![download PDF file pdf](img/file_PDF.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Behavioural Pattern Discovery from Collections of Egocentric Photo-Streams |
Type |
Conference Article |
|
Year |
2020 |
Publication ![sorted by Publication field, ascending order (up)](img/sort_asc.gif) |
ECCV Workshops |
Abbreviated Journal |
|
|
|
Volume |
12538 |
Issue |
|
Pages |
469-484 |
|
|
Keywords |
|
|
|
Abstract |
The automatic discovery of behaviour is of high importance when aiming to assess and improve the quality of life of people. Egocentric images offer a rich and objective description of the daily life of the camera wearer. This work proposes a new method to identify a person’s patterns of behaviour from collected egocentric photo-streams. Our model characterizes time-frames based on the context (place, activities and environment objects) that define the images composition. Based on the similarity among the time-frames that describe the collected days for a user, we propose a new unsupervised greedy method to discover the behavioural pattern set based on a novel semantic clustering approach. Moreover, we present a new score metric to evaluate the performance of the proposed algorithm. We validate our method on 104 days and more than 100k images extracted from 7 users. Results show that behavioural patterns can be discovered to characterize the routine of individuals and consequently their lifestyle. |
|
|
Address |
Virtual; August 2020 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
ECCVW |
|
|
Notes |
MILAB; no proj |
Approved |
no |
|
|
Call Number |
Admin @ si @ MTM2020 |
Serial |
3528 |
|
Permanent link to this record |
|
|
|
|
Author |
Idoia Ruiz; Bogdan Raducanu; Rakesh Mehta; Jaume Amores |
![download PDF file pdf](img/file_PDF.gif)
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Optimizing speed/accuracy trade-off for person re-identification via knowledge distillation |
Type |
Journal Article |
|
Year |
2020 |
Publication ![sorted by Publication field, ascending order (up)](img/sort_asc.gif) |
Engineering Applications of Artificial Intelligence |
Abbreviated Journal |
EAAI |
|
|
Volume |
87 |
Issue |
|
Pages |
103309 |
|
|
Keywords |
Person re-identification; Network distillation; Image retrieval; Model compression; Surveillance |
|
|
Abstract |
Finding a person across a camera network plays an important role in video surveillance. For a real-world person re-identification application, in order to guarantee an optimal time response, it is crucial to find the balance between accuracy and speed. We analyse this trade-off, comparing a classical method, that comprises hand-crafted feature description and metric learning, in particular, LOMO and XQDA, to deep learning based techniques, using image classification networks, ResNet and MobileNets. Additionally, we propose and analyse network distillation as a learning strategy to reduce the computational cost of the deep learning approach at test time. We evaluate both methods on the Market-1501 and DukeMTMC-reID large-scale datasets, showing that distillation helps reducing the computational cost at inference time while even increasing the accuracy performance. |
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
LAMP; 600.109; 600.120 |
Approved |
no |
|
|
Call Number |
Admin @ si @ RRM2020 |
Serial |
3401 |
|
Permanent link to this record |
|
|
|
|
Author |
Thomas B. Moeslund; Sergio Escalera; Gholamreza Anbarjafari; Kamal Nasrollahi; Jun Wan |
![goto web page url](img/www.gif)
|
|
Title |
Statistical Machine Learning for Human Behaviour Analysis |
Type |
Journal Article |
|
Year |
2020 |
Publication ![sorted by Publication field, ascending order (up)](img/sort_asc.gif) |
Entropy |
Abbreviated Journal |
ENTROPY |
|
|
Volume |
25 |
Issue |
5 |
Pages |
530 |
|
|
Keywords |
action recognition; emotion recognition; privacy-aware |
|
|
Abstract |
|
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
HuPBA; no proj |
Approved |
no |
|
|
Call Number |
Admin @ si @ MEA2020 |
Serial |
3441 |
|
Permanent link to this record |
|
|
|
|
Author |
Razieh Rastgoo; Kourosh Kiani; Sergio Escalera |
![goto web page url](img/www.gif)
|
|
Title |
Hand sign language recognition using multi-view hand skeleton |
Type |
Journal Article |
|
Year |
2020 |
Publication ![sorted by Publication field, ascending order (up)](img/sort_asc.gif) |
Expert Systems With Applications |
Abbreviated Journal |
ESWA |
|
|
Volume |
150 |
Issue |
|
Pages |
113336 |
|
|
Keywords |
Multi-view hand skeleton; Hand sign language recognition; 3DCNN; Hand pose estimation; RGB video; Hand action recognition |
|
|
Abstract |
Hand sign language recognition from video is a challenging research area in computer vision, which performance is affected by hand occlusion, fast hand movement, illumination changes, or background complexity, just to mention a few. In recent years, deep learning approaches have achieved state-of-the-art results in the field, though previous challenges are not completely solved. In this work, we propose a novel deep learning-based pipeline architecture for efficient automatic hand sign language recognition using Single Shot Detector (SSD), 2D Convolutional Neural Network (2DCNN), 3D Convolutional Neural Network (3DCNN), and Long Short-Term Memory (LSTM) from RGB input videos. We use a CNN-based model which estimates the 3D hand keypoints from 2D input frames. After that, we connect these estimated keypoints to build the hand skeleton by using midpoint algorithm. In order to obtain a more discriminative representation of hands, we project 3D hand skeleton into three views surface images. We further employ the heatmap image of detected keypoints as input for refinement in a stacked fashion. We apply 3DCNNs on the stacked features of hand, including pixel level, multi-view hand skeleton, and heatmap features, to extract discriminant local spatio-temporal features from these stacked inputs. The outputs of the 3DCNNs are fused and fed to a LSTM to model long-term dynamics of hand sign gestures. Analyzing 2DCNN vs. 3DCNN using different number of stacked inputs into the network, we demonstrate that 3DCNN better capture spatio-temporal dynamics of hands. To the best of our knowledge, this is the first time that this multi-modal and multi-view set of hand skeleton features are applied for hand sign language recognition. Furthermore, we present a new large-scale hand sign language dataset, namely RKS-PERSIANSIGN, including 10′000 RGB videos of 100 Persian sign words. Evaluation results of the proposed model on three datasets, NYU, First-Person, and RKS-PERSIANSIGN, indicate that our model outperforms state-of-the-art models in hand sign language recognition, hand pose estimation, and hand action recognition. |
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
|
|
|
Notes |
HuPBA; no proj |
Approved |
no |
|
|
Call Number |
Admin @ si @ RKE2020a |
Serial |
3411 |
|
Permanent link to this record |
|
|
|
|
Author |
Ciprian Corneanu; Meysam Madadi; Sergio Escalera; Aleix Martinez |
![download PDF file pdf](img/file_PDF.gif)
|
|
Title |
Explainable Early Stopping for Action Unit Recognition |
Type |
Conference Article |
|
Year |
2020 |
Publication ![sorted by Publication field, ascending order (up)](img/sort_asc.gif) |
Faces and Gestures in E-health and welfare workshop |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
693-699 |
|
|
Keywords |
|
|
|
Abstract |
A common technique to avoid overfitting when training deep neural networks (DNN) is to monitor the performance in a dedicated validation data partition and to stop
training as soon as it saturates. This only focuses on what the model does, while completely ignoring what happens inside it.
In this work, we open the “black-box” of DNN in order to perform early stopping. We propose to use a novel theoretical framework that analyses meso-scale patterns in the topology of the functional graph of a network while it trains. Based on it,
we decide when it transitions from learning towards overfitting in a more explainable way. We exemplify the benefits of this approach on a state-of-the art custom DNN that jointly learns local representations and label structure employing an ensemble of dedicated subnetworks. We show that it is practically equivalent in performance to early stopping with patience, the standard early stopping algorithm in the literature. This proves beneficial for AU recognition performance and provides new insights into how learning of AUs occurs in DNNs. |
|
|
Address |
Virtual; November 2020 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
FGW |
|
|
Notes |
HUPBA; |
Approved |
no |
|
|
Call Number |
Admin @ si @ CME2020 |
Serial |
3514 |
|
Permanent link to this record |
|
|
|
|
Author |
Anna Esposito; Terry Amorese; Nelson Maldonato; Alessandro Vinciarelli; Maria Ines Torres; Sergio Escalera; Gennaro Cordasco |
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Seniors’ ability to decode differently aged facial emotional expressions |
Type |
Conference Article |
|
Year |
2020 |
Publication ![sorted by Publication field, ascending order (up)](img/sort_asc.gif) |
Faces and Gestures in E-health and welfare workshop |
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
716-722 |
|
|
Keywords |
|
|
|
Abstract |
|
|
|
Address |
Virtual; November 2020 |
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Summary Language |
|
Original Title |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Medium |
|
|
|
Area |
|
Expedition |
|
Conference |
FGW |
|
|
Notes |
HUPBA |
Approved |
no |
|
|
Call Number |
Admin @ si @ EAM2020 |
Serial |
3515 |
|
Permanent link to this record |